{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/80871"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/80871","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Frequency Based Classification of Damage in Structures","abstract":"M.S.","abstract_html":"M.S.","abstract_has_math":false,"creators":["Kasi, Zarak"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Liang, Xiao","Civil, Structural and Environmental Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-10-29T16:47:44Z","date_published":"2019-10-29T16:47:44Z","updated_at":"2026-07-27T19:05:25Z","subjects":["civil engineering"],"languages":["eng"],"rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10477/80871","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Liang, Xiao","Civil, Structural and Environmental Engineering"]},{"key":"dc:creator","label":"Author","values":["Kasi, Zarak"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-10-29T16:47:44Z","2019","2019-08-01 21:20:08"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["civil engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/10477/80871"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["M.S.","Structural health monitoring (SHM) has gained much importance over the years. This is due to SHM being able to assess damage in a structure in a more economical and efficient way. There has been much emphasis on this type of research and new types of damage features are being proposed. The vibration-based techniques in SHM are classified into two types: 1) Signal based methods; 2) Modal based methods. The modal based methods have some shortcomings when identifying damage as damage is not a local phenomenon and the modal parameters may not quite identify damage efficiently. The signal based methods such as the fast Fourier transform (FFT) and the wavelet transform (WT) identify the changes in the structure directly through proper signal processing.This study examines fast Fourier transform (FFT) and wavelet packet transform (WPT) as damage features for buildings and seeks to understand the behavior of the structure when damaged in terms of frequency content on a global scale. The damage features were used to classify a 3-class classification as Immediate Occupancy, Life Safety and Collapse prevention as well as classifying a 2-class classification as Damaged or Undamaged. The spectral lines of the FFT were used as damage features whereas the energy, Shannon entropy, and log-energy entropy measures were used as damage features for the WPT.Neighborhood component analysis (NCA) was used for the purpose of dimension reduction and identification of the best set of features in FFT and WPT. There were three types of algorithms used for classification in this thesis which are the K-nearest neighbors (KNN), linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA). Noise was also added to the dataset to simulate real life conditions and the accuracy of the model was checked again.The WPT was found to have slightly better accuracy results than FFT in the noise dataset, whereas the FFT performed better than WPT on the no noise dataset."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Frequency Based Classification of Damage in Structures"]}]}],"canonical_facts":{"dc:contributor":["Liang, Xiao","Civil, Structural and Environmental Engineering"],"dc:creator":["Kasi, Zarak"],"dc:date":["2019-10-29T16:47:44Z","2019","2019-08-01 21:20:08"],"dc:description":["M.S.","Structural health monitoring (SHM) has gained much importance over the years. This is due to SHM being able to assess damage in a structure in a more economical and efficient way. There has been much emphasis on this type of research and new types of damage features are being proposed. The vibration-based techniques in SHM are classified into two types: 1) Signal based methods; 2) Modal based methods. The modal based methods have some shortcomings when identifying damage as damage is not a local phenomenon and the modal parameters may not quite identify damage efficiently. The signal based methods such as the fast Fourier transform (FFT) and the wavelet transform (WT) identify the changes in the structure directly through proper signal processing.This study examines fast Fourier transform (FFT) and wavelet packet transform (WPT) as damage features for buildings and seeks to understand the behavior of the structure when damaged in terms of frequency content on a global scale. The damage features were used to classify a 3-class classification as Immediate Occupancy, Life Safety and Collapse prevention as well as classifying a 2-class classification as Damaged or Undamaged. The spectral lines of the FFT were used as damage features whereas the energy, Shannon entropy, and log-energy entropy measures were used as damage features for the WPT.Neighborhood component analysis (NCA) was used for the purpose of dimension reduction and identification of the best set of features in FFT and WPT. There were three types of algorithms used for classification in this thesis which are the K-nearest neighbors (KNN), linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA). Noise was also added to the dataset to simulate real life conditions and the accuracy of the model was checked again.The WPT was found to have slightly better accuracy results than FFT in the noise dataset, whereas the FFT performed better than WPT on the no noise dataset."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/80871"],"dc:language":["eng"],"dc:publisher":["State University of New York at Buffalo"],"dc:rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"dc:subject":["civil engineering"],"dc:title":["Frequency Based Classification of Damage in Structures"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T19:05:25Z"}